Sold by: Yobitel
Deployed on AWS
This product has charges associated with it for expert support, configuration, and maintenance services. OpenAI GPT OSS 20B is an open source large language model inference platform, offering advanced capabilities in natural language processing, text generation, summarization, and AI-driven automation. Preconfigured for GPU acceleration on AWS, it enables efficient deployment of generative AI applications for research, enterprise, and production environments.
Overview
This is a repackaged open source software product wherein additional charges apply for expert support, pre configuration, and ongoing maintenance services. OpenAI GPT OSS 20B is a pre configured large language model inference environment designed for rapid deployment on AWS GPU instances. It provides advanced natural language processing capabilities including text generation, summarization, question answering, and conversational AI. The AMI comes pre installed with NVIDIA GPU drivers, CUDA, PyTorch, and Hugging Face Transformers, ensuring high performance inference out of the box. Automation scripts simplify environment setup, model loading, and scaling, allowing users to start running inference immediately after launch. Pre installed GPT OSS 20B Model: Ready to use LLM optimized for AWS GPU instances. GPU Accelerated Inference: Integrated CUDA for high speed, parallelized execution. AI Powered Applications: Supports chatbots, code generation, document summarization, and enterprise NLP workloads. Secure & Flexible Access: Expose APIs or integrate with existing applications for real time AI solutions. Customizable & Scalable: Open source foundation allows fine tuning, extensions, and large scale deployment. Comprehensive Documentation: Step by step instructions included for deployment, configuration, and usage.
Highlights
- GPU accelerated GPT OSS 20B ready to use within minutes skip complex installations and start deploying LLM inference on AWS instantly.
- Pre installed Hugging Face Transformers, PyTorch, and CUDA ensure smooth, optimized inference workflows with minimal setup.
- Automation scripts and endpoint ready configurations deliver seamless instance startup, efficient GPU utilization, and scalable AI deployments.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
g5.12xlarge Recommended | $0.07 |
Dimensions summary
You pay by the hour for this inference server running on a single g5.12xlarge GPU instance. This is the only pricing dimension offered, so there are no tiers or size options to compare. Billing is usage-based, meaning charges accrue for each hour the instance runs. You launch it through your AWS account, and all charges appear on your existing AWS bill. The environment comes pre-configured with GPU drivers and text-generation tools, so the hourly rate covers a ready-to-run deployment rather than a per-token or per-request charge.
Top-of-mind questions for buyers
The g5.12xlarge instance provides multiple NVIDIA A10G GPUs, each with 24GB of memory. This gives you the GPU capacity to run the pre-configured inference server. You pay for each hour this instance runs, regardless of how many text-generation requests you send.
The hourly software charge applies only while the instance runs. A fully stopped instance stops accruing the software fee. However, stopped instances may still incur underlying AWS storage charges for attached volumes. The metered rate covers running time, not idle or powered-off states.
No. This is instance-hour billing, not per-token or per-request. You pay a flat hourly rate for the running server regardless of request volume. High-throughput usage costs the same per hour as light usage, so continuous workloads spread the fixed hourly cost across more requests.
www.yobitel.com
Helpful?
Vendor refund policy
Take advantage of a complimentary 5 day software stack trial period with subsequent pay as you go charges. Please note that refunds will only be issued in the event of identified stack issues. Kindly note that refunds will not be provided for infrastructure failures, downtimes resulting from misconfiguration, or any other issues with AWS infrastructure.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
We proudly introduce the GPU Optimized GPT OSS 20B AMI an on demand generative AI inference solution built for developers, researchers, and enterprises. This version emphasizes performance, scalability, and ease of use with pre installed NVIDIA drivers, Hugging Face Transformers, PyTorch, and automation scripts for seamless LLM inference on AWS GPU instances.
Additional details
Usage instructions
Refer to our user manual for HPC Optimized Pack for GPT OSS 20B Inference Solutions Yobitel GPT OSS 20B LLM Inference Server with step by step methods Please contact Yobitel customer support in case you require further assistance. Email: support@yobitel.com
Support
Vendor support
We, Yobitel - Cloud-Native Application Stack and Cloud Consulting Services company, offer Free Training, Post Migration & Go-Live support, and Enhanced care support with AWS Chime 24/7 support to ensure a smooth transition. Our team of experts is well-versed in AWS Managed Cloud Services and provides businesses with the necessary guidance and support to ensure a successful transition to the cloud. Learning Resources: Yobitel - Cloud Native Service Provider Resource URL:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Built on openSUSE Linux, this product provides private AI using the ChatGPT OSS 20b model with 20 billion parameters. MultiCortex HPC (High-Performance Computing) allows you to boost your AI's response quality. This is a plug-and-play, low-cost product with no token fees.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.